Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and indicators of examples or instances within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì¹Ń
    -0.17
    ez
    -0.15
    nee
    -0.15
    kara
    -0.15
    VERTISEMENT
    -0.15
    akk
    -0.15
    arness
    -0.14
    ãģ¯ãģļ
    -0.14
    IENTATION
    -0.14
    åıĬåħ¶
    -0.14
    POSITIVE LOGITS
     example
    0.64
    ä¾ĭå¦Ĥ
    0.59
     напÑĢимеÑĢ
    0.56
     ÐĿапÑĢимеÑĢ
    0.55
     napÅĻÃŃklad
    0.53
     ÙħØ«ÙĦا
    0.51
    example
    0.49
     examples
    0.47
     Example
    0.47
     napÅĻ
    0.45
    Act Density 0.466%

    No Known Activations